Dissemination network design for wide-area publish/subscribe.
We study the problem of assigning subscribers to brokers in a wide-area content-based publish/subscribe system, considering not only similarities in subscription interests but also their network locations and event distribution.
The optimization problem that balances multiple performance criteria including bandwidth, delay, and load balance
NP-complete, so systems have turned to heuristics and/or simpler
algorithms that ignore some performance criteria. Evaluating
these approaches has been challenging because optimal solutions
remain elusive for realistic problem sizes. To enable proper
evaluation, we develop a Monte Carlo approximation algorithm
with good theoretical properties and robustness to workload
Albert Yu, Pankaj K. Agarwal, and Jun Yang. "Subscriber assignment for wide-area content-based publish/subscribe." In IEEE Transactions on Knowledge and Data Engineering
, 24(10):1833-1847, 2012. Invited as a special selection from ICDE 2011. paper and supplemental
Albert Yu, Pankaj K. Agarwal, and Jun Yang. "Subscriber Assignment for Wide-Area Content-Based Publish/Subscribe." In Proceedings of the 27th International Conference on Data Engineering (ICDE '11), Hannover, Germany, April 2011. paper.
Albert Yu, Pankaj K. Agarwal, and Jun Yang. "Generating Wide-Area Content-Based Publish/Subscribe Workloads." In Proceedings of the 5th International Workshop on Networking Meets Databases (NetDB '09), Big Sky, Montana, USA, October 2009. paper.